Modeling daily suspended sediment load using improved support vector machine model and genetic algorithm

Rahgoshay, Mitra; Feiznia, Sadat; Arian, Mehran; Hashemi, Seyed Ali Asghar

doi:10.1007/s11356-018-3533-6

Cited by 24 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each water quality index method has a rating scale to express the status of water quality concerning the index value of the lake at selected sampling points. This indexing method has seen widespread use since its commencement and was employed by multiple states and countries [ 25 – 27 ].…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Pollution Status and Detection of the Reason for the Death of Fish in Chamo Lake, Ethiopia

Reddythota

Timotewos

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

Chamo Lake is the third largest rift valley lake and one of the major economic sources for the communities in the Southern region, Ethiopia. The lake’s quality is deteriorating due to the untreated wastewater, and sediment inflow resulting in the death of fish was observed during the dry season. The research aims to determine the water quality status using water quality indices, in addition to identifying the reason for the death of fish in the dry season in Chamo Lake. The water samples were drawn from 5 sampling points by composite sampling method during the dry and wet seasons of the year, and we analyzed 22 water quality parameters. Ammonia (14–23.6 mg/l), phosphates (0.30–1.10 mg/l), BOD (25.32–60 mg/l), COD (40–160 mg/l), and chlorophyll (19.64–31.87 μg/L) concentrations were above the permissible limits, and DO (5.20–6.70 mg/l) was below the acceptable limit in the lake as per EPA standards concerning temperature. The values of both the water quality indices of CCMEWQI (13.90–18.40) and NSFWQI (38.59–49.63) indicated that the water quality was “poor” and “bad,” respectively. The death of fish might be due to high concentrations of ammonia and nutrients in the dry season.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluation of Pollution Status and Detection of the Reason for the Death of Fish in Chamo Lake, Ethiopia

Reddythota

Timotewos

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning algorithms were utilized by many researchers to predict most water quality parameters accurately and proved its efficiency (Rahgoshay et al 2018 ; Ho et al 2019 ; Najah Ahmed et al 2019 ). In this study, four different machine learning algorithms, namely multi-layer perceptron (MLP), support vector machine (SVM), random forest (RF), and boosted decision tree (BDT), have been proposed to predict the changes in water quality parameters.…”

Section: Methodsmentioning

confidence: 99%

Surface water quality status and prediction during movement control operation order under COVID-19 pandemic: Case studies in Malaysia

Najah

Teo

Fai

et al. 2021

Int. J. Environ. Sci. Technol.

View full text Add to dashboard Cite

Global concerns have been observed due to the outbreak and lockdown causal-based COVID-19, and hence, a global pandemic was announced by the World Health Organization (WHO) in January 2020. The Movement Control Order (MCO) in Malaysia acts to moderate the spread of COVID-19 through the enacted measures. Furthermore, massive industrial, agricultural activities and human encroachment were significantly reduced following the MCO guidelines. In this study, first, a reconnaissance survey was carried out on the effects of MCO on the health conditions of two urban rivers (i.e., Rivers of Klang and Penang) in Malaysia. Secondly, the effect of MCO lockdown on the water quality index (WQI) of a lake (Putrajaya Lake) in Malaysia is considered in this study. Finally, four machine learning algorithms have been investigated to predict WQI and the class in Putrajaya Lake. The main observations based on the analysis showed that noticeable enhancements of varying degrees in the WQI had occurred in the two investigated rivers. With regard to Putrajaya Lake, there is a significant increase in the WQI Class I, from 24% in February 2020 to 94% during the MCO month of March 2020. For WQI prediction, Multi-layer Perceptron (MLP) outperformed other models in predicting the changes in the index with a high level of accuracy. For sensitivity analysis results, it is shown that NH3-N and COD play vital rule and contributing significantly to predicting the class of WQI, followed by BOD, while the remaining three parameters (i.e. pH, DO, and TSS) exhibit a low level of importance.

show abstract

“…(Olyaie et al, 2015) predicted SSL in the Flathead River and in the Santa Clara River using ANN, ANFIS and WANN models, obtaining 𝑅 2 = 0.662, 0.683 and 0.894, respectively. (Rahgoshay et al, 2018) modeled daily SSL using M5, SVM-GA (Genetic Algorithm) and MARS models, with…”

Section: [Figure 6]mentioning

confidence: 99%

Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis

Sharafati

Asadollah

Motta

et al. 2020

Hydrological Sciences Journal

View full text Add to dashboard Cite

Ensemble machine learning models have been widely used in hydro-systems modeling as robust prediction tools that combine multiple decision trees. In this study, three newly developed ensemble machine learning models, namely Gradient Boost Regression (GBR), Ada Boost Regression (ABR) and Random Forest Regression (RFR) are proposed for prediction of Suspended Sediment Load (SSL), and their prediction performance and related uncertainty are assessed. The Suspended Sediment Load (SSL) of the Mississippi River, which is one of the major world rivers and is significantly affected by sedimentation, is predicted based on daily values of river Discharge (Q) and Suspended Sediment Concentration (SSC). Based on performance metrics and visualization, the RFR model shows a slight lead in prediction performance. The uncertainty analysis also indicates that the input variable combination has more impact on the obtained predictions than the model structure selection.

show abstract

Modeling daily suspended sediment load using improved support vector machine model and genetic algorithm

Cited by 24 publications

References 34 publications

Evaluation of Pollution Status and Detection of the Reason for the Death of Fish in Chamo Lake, Ethiopia

Evaluation of Pollution Status and Detection of the Reason for the Death of Fish in Chamo Lake, Ethiopia

Surface water quality status and prediction during movement control operation order under COVID-19 pandemic: Case studies in Malaysia

Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis

Contact Info

Product

Resources

About